CASE REPORT: A 34-year-old woman with intractable epigastric pain was referred to have repeated endoscopy with biopsy. She was found to multiple gastric erosions and nodules that were diagnosed as inflammatory lesions both endoscopically and histologically. Meanwhile, she developed an acute onset of severe back pain associated with a pathologic compression fracture in the T3 thoracic vertebral body. Imaging studies disclosed a disseminated systemic disease involving abdominopelvic lymph nodes and cervical and thoracic vertebral bodies. The needle biopsy of the pelvic lymph node disclosed diffuse proliferation of monomorphic small round cells that were diffusely positive for CD30 and ALK. A diagnosis of ALK+ ALCL with a monomorphic SC pattern was rendered.
DISCUSSION: A retrospective review of the gastric biopsies with the aid of immunohistochemistry enabled us to recognise the presence of lymphomatous infiltrates with a mixed LH and SC pattern in every piece of gastric biopsies that were repeatedly misdiagnosed as inflammatory lesions. This case illustrates a significant diagnostic pitfall of the LH- and SC-patterns in ALK+ ALCL, in which the tumour cells featuring lymphoid, plasmacytoid or histiocytoid appearance can be masqueraded as inflammatory cells.
MATERIALS AND METHODS: This was a retrospective study using computed tomography (CT) scans from 3 hospitals. Inclusion criteria were scans with 1-5 nodules of diameter ≥5 mm; exclusion criteria were poor-quality scans or those with nodules measuring <5mm in diameter. In the lesion detection phase, 2,147 nodules from 219 scans were used to develop and train the deep learning 3D-CNN to detect lesions. The 3D-CNN was validated with 235 scans (354 lesions) for sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) analysis. In the path planning phase, Bayesian optimization was used to propose possible needle trajectories for lesion biopsy while avoiding vital structures. Software-proposed needle trajectories were compared with actual biopsy path trajectories from intraprocedural CT scans in 150 patients, with a match defined as an angular deviation of <5° between the 2 trajectories.
RESULTS: The model achieved an overall AUC of 97.4% (95% CI, 96.3%-98.2%) for lesion detection, with mean sensitivity of 93.5% and mean specificity of 93.2%. Among the software-proposed needle trajectories, 85.3% were feasible, with 82% matching actual paths and similar performance between supine and prone/oblique patient orientations (P = .311). The mean angular deviation between matching trajectories was 2.30° (SD ± 1.22); the mean path deviation was 2.94 mm (SD ± 1.60).
CONCLUSIONS: Segmentation, lesion detection, and path planning for CT-guided lung biopsy using an AI-guided software showed promising results. Future integration with automated robotic systems may pave the way toward fully automated biopsy procedures.