Background and Objectives: To date, the gold standard of care for bone sarcomas is limb salvage surgical resection. In cases where the tumor arises in the distal femur or proximal tibia near the joint line, knee-sacrificing surgery is typically performed, followed by reconstruction with oncological megaprostheses. This study aims to evaluate the effectiveness of a precise 3D-based surgical approach for knee-sparing tumor resections, assessing its feasibility and its impact on surgical, oncological, and functional outcomes. Materials and Methods: This single-center retrospective study presents the surgical and oncological outcomes of knee-sparing surgeries following bone sarcoma resections. All patients underwent either intercalary or geographic resection, and reconstruction was tailored to each patient, using either an allograft or a titanium alloy Ti64 implant, depending on the specific requirements of the case. Results: A total of 23 patients (average age 21.04 years, 14 males) were included, with an average postoperative follow-up of 58 months (range: 12–102 months). Clear surgical margins were achieved in all patients, with 16 patients (69.5%) showing wide negative margins (R0) and the rest showing close negative margins (R1). Resections were primarily intercalary (17 patients, 73.9%), with 6 patients (26.1%) undergoing geographic resections. Reconstruction methods included allografts (9 patients, 39.3%), vascularized fibula and allograft (8 patients, 34.7%), and printed Ti64 cage reconstructions (6 patients, 26.0%). At the last follow-up, 19 patients (82.6%) were disease-free, 3 patients (13.4%) were alive with evidence of disease, and 1 patient (4%) was dead of disease. Complications included four cases of non-union that required revision surgery, as well as two local recurrences, which necessitated revision surgery to a modular endoprosthesis and above-knee amputation. The average MSTS at the final follow-up was 23.16 ± 5.91. Conclusions: The use of 3D-printed PSIs for knee-sparing bone tumor resections has emerged as the gold standard, enhancing both surgical and oncological outcomes. A future challenge lies in improving reconstruction techniques, shifting from traditional allografts to customized Ti64 printed lattice implants. As personalized healthcare and additive manufacturing continue to advance, the future of orthopedic oncology will likely see more precise, durable, and biologically integrated implants, further improving patient outcomes.

Desmoid tumors (DTs) are non-metastasizing and locally aggressive soft-tissue mesenchymal neoplasms. Those that become enlarged often become locally invasive and cause significant morbidity. DTs have a varied pattern of clinical presentation, with up to 50–60% not growing after diagnosis and 20–30% shrinking or even disappearing after initial progression. Enlarging tumors are considered unstable and progressive. The management of symptomatic and enlarging DTs is challenging, and primarily consists of chemotherapy. Despite wide surgical resection, DTs carry a rate of local recurrence as high as 50%. There is a consensus that contrast-enhanced magnetic resonance imaging (MRI) or, alternatively, computerized tomography (CT) is the preferred modality for monitoring DTs. Each uses Response Evaluation Criteria in Solid Tumors version 1.1 (RECIST 1.1), which measures the largest diameter on axial, sagittal, or coronal series. This approach, however, reportedly lacks accuracy in detecting response to therapy and fails to detect tumor progression, thus calling for more sophisticated methods. The objective of this study was to detect unique features identified by deep learning that correlate with the future clinical course of the disease. Between 2006 and 2019, 51 patients (mean age 41.22 ± 15.5 years) who had a tissue diagnosis of DT were included in this retrospective single-center study. Each had undergone at least three MRI examinations (including a pretreatment baseline study), and each was followed by orthopedic oncology specialists for a median of 38.83 months (IQR 44.38). Tumor segmentations were performed on a T2 fat-suppressed treatment-naive MRI sequence, after which the segmented lesion was extracted to a three-dimensional file together with its DICOM file and run through deep learning software. The results of the algorithm were then compared to clinical data collected from the patients’ medical files. There were 28 males (13 stable) and 23 females (15 stable) whose ages ranged from 19.07 to 83.33 years. The model was able to independently predict clinical progression as measured from the baseline MRI with an overall accuracy of 93% (93 ± 0.04) and ROC of 0.89 ± 0.08. Artificial intelligence may contribute to risk stratification and clinical decision-making in patients with DT by predicting which patients are likely to progress.