Medical second opinions are common, although little is known about the best processes for obtaining them. This study assesses whether knowledge of a prior physician's diagnosis influences consulting physicians' diagnoses.
BACKGROUND Research examining the role of second opinions in pathology for diagnosis of melanocytic lesions is limited. OBJECTIVE To assess current laboratory policies, clinical use of second opinions, and pathologists' perceptions of second opinions for melanocytic lesions. MATERIALS AND METHODS Cross-sectional data collected from 207 pathologists in 10 US states who diagnose melanocytic lesions. The web-based survey ascertained pathologists' professional information, laboratory second opinion policy, use of second opinions, and perceptions of second opinion value for melanocytic lesions. RESULTS Laboratory policies required second opinions for 31% of pathologists and most commonly required for melanoma in situ (26%) and invasive melanoma (30%). In practice, most pathologists reported requesting second opinions for melanocytic tumors of uncertain malignant potential (85%) and atypical Spitzoid lesions (88%). Most pathologists perceived that second opinions increased interpretive accuracy (78%) and protected them from malpractice lawsuits (62%). CONCLUSION Use of second opinions in clinical practice is greater than that required by laboratory policies, especially for melanocytic tumors of uncertain malignant potential and atypical Spitzoid lesions. Quality of care in surgical interventions for atypical melanocytic proliferations critically depends on the accuracy of diagnosis in pathology reporting. Future research should examine the extent to which second opinions improve accuracy of melanocytic lesion diagnosis.
Deep learning techniques offer improvements in computer-aided diagnosis systems. However, acquiring image domain annotations is challenging due to the knowledge and commitment required of expert pathologists. Pathologists often identify regions in whole slide images with diagnostic relevance rather than examining the entire slide, with a positive correlation between the time spent on these critical image regions and diagnostic accuracy. In this paper, a heatmap is generated to represent pathologists' viewing patterns during diagnosis and used to guide a deep learning architecture during training. The proposed system outperforms traditional approaches based on color and texture image characteristics, integrating pathologists' domain expertise to enhance region of interest detection without needing individual case annotations. Evaluating our best model, a U-Net model with a pre-trained ResNet-18 encoder, on a skin biopsy whole slide image dataset for melanoma diagnosis, shows its potential in detecting regions of interest, surpassing conventional methods with an increase of 20%, 11%, 22%, and 12% in precision, recall, F1-score, and Intersection over Union, respectively. In a clinical evaluation, three dermatopathologists agreed on the model's effectiveness in replicating pathologists' diagnostic viewing behavior and accurately identifying critical regions. Finally, our study demonstrates that incorporating heatmaps as supplementary signals can enhance the performance of computer-aided diagnosis systems. Without the availability of eye tracking data, identifying precise focus areas is challenging, but our approach shows promise in assisting pathologists in improving diagnostic accuracy and efficiency, streamlining annotation processes, and aiding the training of new pathologists.
In this study, we propose the Ductal Instance-Oriented Pipeline (DIOP) that contains a duct-level instance segmentation model, a tissue-level semantic segmentation model, and three-levels of features for diagnostic classification. Based on recent advancements in instance segmentation and the Mask R-CNN model, our duct-level segmenter tries to identify each ductal individual inside a microscopic image; then, it extracts tissue-level information from the identified ductal instances. Leveraging three levels of information obtained from these ductal instances and also the histopathology image, the proposed DIOP outperforms previous approaches (both feature-based and CNN-based) in all diagnostic tasks; for the four-way classification task, the DIOP achieves comparable performance to general pathologists in this unique dataset. The proposed DIOP only takes a few seconds to run in the inference time, which could be used interactively on most modern computers. More clinical explorations are needed to study the robustness and generalizability of this system in the future.
Objective To understand the sophisticated nature of coming to consensus when diagnosing complex melanocytic lesions among a panel of experienced dermatopathologists. Methods A total of 240 melanocytic lesions were assessed independently by three experienced dermatopathologists with their diagnoses mapped into one of five Melanocytic Pathology Assessment Tool and Hierarchy for Diagnosis ( MPATH‐DX ) categories: (I) nevus/mild atypia, ( II ) moderate atypia, ( III ) severe atypia/melanoma in situ , ( IV ) T1a invasive melanoma and (V) ≥ T1b invasive melanoma. The dermatopathologists then discussed the cases, using a modified Delphi method to facilitated consensus building for cases with discordant diagnoses. Results For most cases, a majority of interpretations (two or three of three) agreed with the consensus diagnosis in 95% of Category I, 64% of Category II , 84% of Category III , 88% for Category IV and 100% of Category V cases. Disagreements were typically due to diagnostic threshold differences (64.5%), differing contents on slides even though the slides were sequential cuts (18.5%), and missed findings (15.3%). Disagreements were resolved via discussion of histopathologic features and their significance while reviewing the slides using a multi‐headed microscope, considering treatment recommendations, citing existing literature, reviewing additional slides for a case, and choosing a provisional/borderline diagnosis to capture diverse opinions. All experienced pathologists participating in this study reported that the process of coming to consensus was challenging for borderline cases and may have represented compromise rather than consensus. They also reported the process changed their approaches to diagnosing complex melanocytic lesions. Conclusions The most frequent reason for disagreement of experienced dermatopathologists was differences in diagnostic thresholds related to observer viewpoints. A range of approaches was needed to come to consensus, and this may guide pathology groups who do not currently hold consensus conferences.
Congenital fibrosarcoma (CFS) is a pediatric spindle cell tumor of the soft tissues that usually presents before the age of 2 years. Although these tumors display histologic features of malignancy and frequently recur, they have a relatively good prognosis and only rarely metastasize. CFS must therefore be differentiated from more aggressive spindle cell sarcomas that occur during childhood, particularly adult-type fibrosarcoma (ATFS), which can have an identical morphology. CFS must also be distinguished from benign but cellular fibroblastic lesions of the same age group, including infantile fibromatosis (IFB) and myofibromatosis (MFB). Unfortunately, standard pathologic examination often does not differentiate CFS from these other conditions. The authors recently identified a novel chromosomal translocation in CFS, t(12;15)(p13;q25), which gives rise to an ETV6-NTRK3 gene fusion. They subsequently developed reverse transcription–polymerase chain reaction (RT-PCR) assays that can detect ETV6-NTRK3 fusion transcripts in CFS frozen or paraffin-embedded tumor specimens. To confirm the use of this assay in the differential diagnosis of CFS, they have screened a larger series of childhood pediatric spindle cell lesions for ETV6-NTRK3 gene fusions, including 11 cases of CFS, 13 malignant spindle cell tumors (including ATFS), and 38 benign spindle cell tumors (including IFB and MFB). Of the 11 cases diagnosed as CFS, 10 showed the ETV6-NTRK3 gene fusion, whereas none of the 51 other malignant or benign spindle cell tumors demonstrated this fusion gene. They also compared their RT-PCR findings with those of conventional cytogenetics and with immunohistochemical detection of the ETV6-NTRK3 protein using antisera to NTRK3. They conclude that RT-PCR analysis is superior to these techniques for the detection of the ETV6-NTRK3 gene fusion in pediatric spindle cell tumors, and it is a reliable and specific modality for the diagnosis of CFS.
