Abstract Background To construct and compare merged models integrating clinical factors, MRI-based radiomics features and deep learning (DL) models for predicting pathological complete response (pCR) to neoadjuvant chemoradiotherapy (nCRT) in patients with locally advanced rectal cancer (LARC). Methods Totally 197 patients with LARC administered surgical resection after nCRT were assigned to cohort 1 (training and test sets); meanwhile, 52 cases were assigned to cohort 2 as a validation set. Radscore and DL models were established for predicting pCR applying pre- and post-nCRT MRI data, respectively. Different merged models integrating clinical factors, Radscore and DL model were constituted. Their predictive performances were validated and compared by receiver operating characteristic (ROC) and decision curve analyses (DCA). Results Merged models were established integrating selected clinical factors, Radscore and DL model for pCR prediction. The areas under the ROC curves (AUCs) of the pre-nCRT merged model were 0.834 (95% CI: 0.737–0.931) and 0.742 (95% CI: 0.650–0.834) in test and validation sets, respectively. The AUCs of the post-nCRT merged model were 0.746 (95% CI: 0.636–0.856) and 0.737 (95% CI: 0.646–0.828) in test and validation sets, respectively. DCA showed that the pretreatment algorithm could yield enhanced clinically benefit than the post-nCRT approach. Conclusions The pre-nCRT merged model including clinical factors, Radscore and DL model constitutes an effective non-invasive tool for pCR prediction in LARC.
To explore the effect of b-value distributions on the repeatability and diagnostic performance of the ADC value in rectal cancer patients using multiple b-values and mono-exponential model diffusion-weighted imaging (DWI). Thirty-two preoperative rectal cancer patients, without receiving neoadjuvant therapy, were scanned on a 3 Tesla magnetic resonance imaging scanner using DWI with 10 b-values ranging from 0 to 2000 s/mm2. The apparent diffusion coefficient (ADC) value was calculated using a mono-exponential model and 31 b-value combinations consisting of 2 to 10 b-values were explored. Regions of interest with the maximum cross-sectional tumour size were outlined on the ADC map by two independent observers. Intraclass correlation coefficients (ICC), coefficient of variation (CV), and Bland-Altman plots between the two observers were calculated and evaluated to determine repeatability. Areas under receiver operating characteristic curves (AUCs) were evaluated for rectal cancer characterization. Correlations between the mean ADC values and T stage were assessed using the Spearman correlation coefficient (ρ). α (= ICC + AUC + |ρ|- CV - |bias|) was defined and used to assess the optimal b-value distribution. Postoperative pathology tests revealed 4 patients with T1, 10 patients with T2, and 18 patients with T3 stages. There were no significant difference in age and sex between the two groups (T1–2 vs. T3). Excellent reproducibility was observed for ADC values between two observers with ICC and CV values ranging from 0.920 to 0.998, and 1.475 to 5.568%, respectively. The mean percent difference and ρ between the paired measurements was ranged from − 2.7 to 1.2% and from − 0.759 to − 0.407, respectively. The b-value combinations with the top three α values were b(0, 1000 s/mm2), b(500, 1500, 2000 s/mm2) and b(100, 1000, 1500 s/mm2) for α = 2.581, 2.571 and 2.569, respectively. The number of b-values and their distributions influenced the repeatability of the ADC values and their diagnostic performance. The optimal b-value combination was 0 and 1000 s/mm2 for DWI examination of rectal cancer patients.
BACKGROUND Large language models, similar to ChatGPT, potentially offer both advantages and challenges when tasked with answering disease-related questions. It is valuable to investigate whether assigning a specific role to these large language models, such as simulating a radiologist, could lead to more appropriate responses. OBJECTIVE To evaluate and compare the accuracy of ChatGPT-4 with the role of a radiologist (ChatGPT-4R) in answering questions related to breast, lung, and prostate cancer with the direct responses provided by ChatGPT-4. METHODS The study utilized 25, 40, and 22 common questions pertinent to breast, lung, and prostate cancer, respectively. These questions were posed to ChatGPT-4 and ChatGPT-4R to yield responses. Subsequently, five radiologists reviewed each question and classified the derived answers into three categories: correct, partially correct, or incorrect. The accuracy of the responses was evaluated employing McNemar tests. RESULTS The analysis of responses related to breast, lung, and prostate cancer showed that ChatGPT-4R answered with an accuracy of 96%, 87.5%, and 100%, respectively. On the other hand, ChatGPT-4's accuracy was 96%, 72.5%, and 95.5% for the same categories. Across all 87 questions, ChatGPT-4R achieved 93.1% correct responses, 4.6% partially correct responses, and 2.3% incorrect responses. In comparison, ChatGPT-4R was more likely to provide correct answers than ChatGPT-4, with a significant difference of 8.0% (P = .02). CONCLUSIONS The performance of ChatGPT-4R exceeds that of ChatGPT-4 in terms of accuracy. However, it remains incapable of providing correct answers to all posed questions. CLINICALTRIAL N/A
The current work aimed to develop a nomogram comprised of MRI-based pelvimetry and clinical factors for predicting the difficulty of rectal surgery for middle and low rectal cancer (RC).Consecutive mid to low RC cases who underwent transabdominal resection between June 2020 and August 2021 were retrospectively enrolled. Univariable and multivariable logistic regression analyses were carried out for identifying factors (clinical factors and MRI-based pelvimetry parameters) independently associated with the difficulty level of rectal surgery. A nomogram model was established with the selected parameters for predicting the probability of high surgical difficulty. The predictive ability of the nomogram model was assessed by the receiver operating characteristic (ROC) curve and decision curve analysis (DCA).A total of 122 cases were included. BMI (OR = 1.269, p = 0.006), pelvic inlet (OR = 1.057, p = 0.024) and intertuberous distance (OR = 0.938, p = 0.001) independently predicted surgical difficulty level in multivariate logistic regression analysis. The nomogram model combining these predictors had an area under the ROC curve (AUC) of 0.801 (95% CI: 0.719-0.868) for the prediction of a high level of surgical difficulty. The DCA suggested that using the nomogram to predict surgical difficulty provided a clinical benefit.The nomogram model is feasible for predicting the difficulty level of rectal surgery, utilizing MRI-based pelvimetry parameters and clinical factors in mid to low RC cases.
Detecting mismatch-repair (MMR) status is crucial for personalized treatment strategies and prognosis in rectal cancer (RC). A preoperative, noninvasive, and cost-efficient predictive tool for MMR is critically needed. Therefore, this study developed and validated machine learning radiomics models for predicting MMR status in patients directly on preoperative MRI scans. Pathologically confirmed RC cases administered surgical resection in two distinct hospitals were examined in this retrospective trial. Totally, 78 and 33 cases were included in the training and test sets, respectively. Then, 65 cases were enrolled as an external validation set. Radiomics features were obtained from preoperative rectal MR images comprising T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), contrast-enhanced T1-weighted imaging (T1WI), and combined multisequences. Four optimal features related to MMR status were selected by the least absolute shrinkage and selection operator (LASSO) method. Support vector machine (SVM) learning was adopted to establish four predictive models, i.e., ModelT2WI, ModelDWI, ModelCE-T1WI, and Modelcombination, whose diagnostic performances were determined and compared by receiver operating characteristic (ROC) curves and decision curve analysis (DCA). Modelcombination had better diagnostic performance compared with the other models in all datasets (all ). The usefulness of the proposed model was confirmed by DCA. Therefore, the present pilot study showed the radiomics model combining multiple sequences derived from preoperative MRI is effective in predicting MMR status in RC cases.
The manual delineation of the lesion is mainly used as a conventional segmentation method, but it is subjective and has poor stability and repeatability. The purpose of this study is to validate the effect of a radiomics model based on MRI derived from two delineation methods in the preoperative T staging of patients with rectal cancer (RC). A total of 454 consecutive patients with pathologically confirmed RC who underwent preoperative MRI between January 2018 and December 2019 were retrospectively analyzed. RC patients were grouped according to whether the muscularis propria was penetrated. Two radiologists segmented lesions, respectively, by minimum delineation (Method 1) and maximum delineation (Method 2), after which radiomics features were extracted. Inter- and intraclass correlation coefficient (ICC) of all features was evaluated. After feature reduction, the support vector machine (SVM) was trained to build a prediction model. The diagnostic performances of models were determined by receiver operating characteristic (ROC) curves. Then, the areas under the curve (AUCs) were compared by the DeLong test. Decision curve analysis (DCA) was performed to evaluate clinical benefit. Finally, 317 patients were assessed, including 152 cases in the training set and 165 cases in the validation set. Moreover, 1288/1409 (91.4%) features of Method 1 and 1273/1409 (90.3%) features of Method 2 had good robustness ( ). The AUCs of Model 1 and Model 2 were 0.808 and 0.903 in the validation set, respectively ( ). DCA showed that the maximum delineation yielded more net benefit. MRI-based radiomics models derived from two segmentation methods demonstrated good performance in the preoperative T staging of RC. The minimum delineation had better stability in feature selection, while the maximum delineation method was more clinically beneficial.
To develop and validate a multimodal MRI-based radiomics nomogram for predicting clinically significant prostate cancer (CS-PCa).Patients who underwent radical prostatectomy with pre-biopsy prostate MRI in three different centers were assessed retrospectively. Totally 141 and 60 cases were included in the training and test sets in cohort 1, respectively. Then, 66 and 122 cases were enrolled in cohorts 2 and 3, as external validation sets 1 and 2, respectively. Two different manual segmentation methods were established, including lesion segmentation and whole prostate segmentation on T2WI and DWI scans, respectively. Radiomics features were obtained from the different segmentation methods and selected to construct a radiomics signature. The final nomogram was employed for assessing CS-PCa, combining radiomics signature and PI-RADS. Diagnostic performance was determined by receiver operating characteristic (ROC) curve analysis, net reclassification improvement (NRI) and decision curve analysis (DCA).Ten features associated with CS-PCa were selected from the model integrating whole prostate (T2WI) + lesion (DWI) for radiomics signature development. The nomogram that combined the radiomics signature with PI-RADS outperformed the subjective evaluation alone according to ROC analysis in all datasets (all p<0.05). NRI and DCA confirmed that the developed nomogram had an improved performance in predicting CS-PCa.The established nomogram combining a biparametric MRI-based radiomics signature and PI-RADS could be utilized for noninvasive and accurate prediction of CS-PCa.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
