Interobserver Variability Among Expert Orthopedic Pathologists for Diagnosis, Histologic Grade, and Determination of the Necessity for Chemotherapy in Osteosarcoma

Dedifferentiation in bone and soft tissue sarcomas: How do we define it? What is prognostically relevant?

Dedifferentiation traditionally is defined by descriptive criteria as a tumor showing an abrupt change in histology from a conventional, classic, low-grade appearing neoplasm to a tumor that is more cellular, pleomorphic and "high grade", with grading typically being performed by subjective criteria. The dedifferentiated areas range from areas with recognizable histologic differentiation which differs from the primary tumor (such as an osteosarcoma arising from a low-grade chondrosarcoma) to areas containing sarcomas without specific histologic differentiation (such as pleomorphic or spindle cell sarcoma). Many, but not all, dedifferentiated tumors are aggressive and associated with significantly shorter survival than their conventional counterparts, even grade 3 conventional tumors. As a result, dedifferentiated tumors are generally considered to be clinically aggressive and as a result, more aggressive surgery or the addition of (neo)adjuvant chemotherapy is often considered. However, long-term (greater than 20 year) survivors are reported in the most common dedifferentiated bone and soft tissue sarcomas. Moreover, use of mitotic criterion for defining dedifferentiation in dedifferentiated liposarcoma as well as grading (by the French system) have been found to be associated with survival. This paper reviews the literature on dedifferentiated chondrosarcoma, dedifferentiated liposarcoma, dedifferentiated chordoma and dedifferentiated parosteal osteosarcoma. As a result of that review, recommendations are advocated to identify evidence-based, objective diagnostic and grading criteria for dedifferentiation that are appropriate for each tumor type. Adding such criteria will improve consistency in diagnosis worldwide, allow easier comparison of clinical research performed on dedifferentiated tumors and help communicate (to patients and clinicians) the tumors with highest risk of clinically aggressive behavior, to allow appropriate and personalized treatment planning.

The use of weakly supervised machine learning for necrosis assessment in patients with osteosarcoma: A pilot study

Percent necrosis (PN) following chemotherapy is a prognostic factor for survival in osteosarcoma. Pathologists estimate PN by calculating tumor viability over an average of whole-slide images (WSIs). This non-standardized, labor-intensive process requires specialized training and has high interobserver variability. Therefore, we aimed to develop a machine-learning model capable of calculating PN in osteosarcoma with similar accuracy to that of a musculoskeletal pathologist. In this proof-of-concept study, we retrospectively obtained six WSIs from two patients with conventional osteosarcomas. A weakly supervised learning model was trained by using coarse and incomplete annotations of viable tumor, necrotic tumor, and nontumor tissue in WSIs. Weakly supervised learning refers to processes capable of creating predictive models on the basis of partially and imprecisely annotated data. Once "trained," the model segmented areas of tissue and determined PN of the same six WSIs. To assess model fidelity, the pathologist also estimated PN of each WSI, and we compared the estimates using Pearson's correlation and mean absolute error (MAE). MAE was 15% over the six samples, and 6.4% when an outlier was removed, for which the model inaccurately labeled cartilaginous tissue. The model and pathologist estimates were strongly, positively correlated (r = 0.85). Thus, we created and trained a weakly supervised machine learning model to segment viable tumor, necrotic tumor, and nontumor and to calculate PN with accuracy similar to that of a musculoskeletal pathologist. We expect improvement can be achieved by annotating cartilaginous and other mesenchymal tissue for better representation of the histological heterogeneity in osteosarcoma.