BM-BronchoLC - A rich bronchoscopy dataset for anatomical landmarks and lung cancer lesion recognition.

Flexible bronchoscopy has revolutionized respiratory disease diagnosis. It offers direct visualization and detection of airway abnormalities, including lung cancer lesions. Accurate identification of airway lesions during flexible bronchoscopy plays an important role in the lung cancer diagnosis. The application of artificial intelligence (AI) aims to support physicians in recognizing anatomical landmarks and lung cancer lesions within bronchoscopic imagery. This work described the development of BM-BronchoLC, a rich bronchoscopy dataset encompassing 106 lung cancer and 102 non-lung cancer patients. The dataset incorporates detailed localization and categorical annotations for both anatomical landmarks and lesions, meticulously conducted by senior doctors at Bach Mai Hospital, Vietnam. To assess the dataset's quality, we evaluate two prevalent AI backbone models, namely UNet++ and ESFPNet, on the image segmentation and classification tasks with single-task and multi-task learning paradigms. We present BM-BronchoLC as a reference dataset in developing AI models to assist diagnostic accuracy for anatomical landmarks and lung cancer lesions in bronchoscopy data.

The impact on anatomical landmark identification after an ultrasound-guided palpation intervention: a pilot study.

Background: To determine whether a discrepancy exists in identifying three musculoskeletal landmarks (medial meniscus, lateral malleolus and lateral epicondyle of the humerus) and whether ultrasound-guided (US-guided) palpation intervention can reduce that discrepancy and improve localization for chiropractic interns. Methods: Sixteen chiropractic interns were asked to identify three subcutaneous anatomical landmarks before/ after the intervention and at a 3-day follow-up. The intervention was a three-minute US-guided demonstration of the landmarks after the intern's initial localization. The primary outcome measure was the change in distance between the intern's landmark identification. Non-normal data were analyzed with the Friedman's and Wilcoxon signed rank tests. Discrepancy between examiner-determined landmarks and intern-identified landmarks at the initial time point was assessed with a 1-sample Wilcoxon signed rank test. Results: All locations demonstrated an initial discrepancy between examiner-determined landmarks and intern-identified landmarks at the initial time point. Overall, a statistically significant difference was noted in the identification of the medial meniscus (p = 0.012) and lateral malleolus (p = 0.001), but not at the lateral epicondyle (p = 0.086). For the before and immediately after comparison, a significant improvement was found with the medial meniscus (p = 0.005) and lateral malleolus (p = 0.002). The 3-day post-intervention comparison found an improvement only for the lateral malleolus (p = 0.008). Conclusion: This pilot study demonstrated palpatory discrepancy at identifying all three landmarks. Our data suggests that US-guided palpation intervention seems to improve an intern's ability to palpate two landmarks (medial meniscus and lateral malleolus) post-intervention.

Radio-Morphometric Evaluation of Greater Palatine Canal and Pterygopalatine Fossa Component: Maxillary Anesthetic Implications.

This is a retrospective analytical cross-sectional study involving 131 cone-beam computed tomography (CBCT) scans of adult (18-99 years) that assessed greater palatine canal (GPC) attributes (length, curvature angle, diameter of curvature) and the type of the trajectory of GPC-pterygopalatine fossa (PPF) component. The GPC is an important landmark that connects the oral cavity and PPF. It contains greater and lesser palatine nerves, along-with descending palatine artery and vein by extending from the inferior part of the PPF to the hard palate. The GPC acts as a pathway for infiltration of local anesthesia. The inferior orbital fissure (IOF) is in close proximity to these vital anatomic structures and hence accurate identification of its location during regional block anesthesia is crucial. This is one of the very few studies investigating these important structures on CBCT scans highlighting the importance of preoperative scans for the anatomic determination. The images were analyzed for the lengths and anatomic paths of the right and left GPC-PPF in sagittal plane. The diameters of the upper (higher bony aspect of PPF) and lower openings (GPC opening) displayed statistically significant differences in the comparison between males and females (P < 0.05). Overestimation or underestimation of the GPC length can cause a lack of anesthesia and undesirable diffusion of the anesthetic solution into the orbit thorough the IOF causing diplopia, or into the cranial cavity. A thorough understanding of GPC length and pathway types is obligatory for proper anesthetic administration and performing any maxillofacial procedures.

Respiratory motion variability of primary tumors and lymph nodes during radiotherapy of locally advanced non-small-cell lung cancers.

BACKGROUND AND PURPOSE: The need for target adjustment due to respiratory motion variation and the value of carina as a motion surrogate is evaluated for locally advanced non-small-cell lung cancer. MATERIAL AND METHODS: Using weekly 4D CTs (with audio-visual biofeedback) of 12 patients, respiratory motion variation of primary tumors (PT), lymph nodes (LN) and carina (C) were determined. RESULTS: Mean (SD) 3D respiratory motion ranges of PT, LN and C were 4 (3), 5 (3) and 5 (3) mm. PT and LN (p = 0.003), and LN and C motion range were correlated (p = 0.03). Only 20 %/5 % of all scans had variations >3 mm/5 mm. Large respiratory motion range on the initial scan was associated with larger during-treatment variations for PT (p = 0.03) and LN (p = 0.001). Mean (SD) 3D relative displacements of PT-C, LN-C and PT-LN were each 6 (2) mm. Variations of displacements >3 mm/5 mm were observed in 28 %/6 % of scans for PT-LN, 20 %/9 % for PT-C, and 20 %/8 % for LN-C. CONCLUSIONS: Motion reassessment is recommended in patients with large initial motion range. Relative motion-related displacements between PT and LN were larger than PT and LN motion alone. Both PT and C appear to be comparable surrogates for LN respiratory motion.

Feasibility of multimodal deformable registration for head and neck tumor treatment planning.

PURPOSE: To investigate the feasibility of using deformable registration in clinical practice to fuse MR and CT images of the head and neck for treatment planning. METHOD AND MATERIALS: A state-of-the-art deformable registration algorithm was optimized, evaluated, and compared with rigid registration. The evaluation was based on manually annotated anatomic landmarks and regions of interest in both modalities. We also developed a multiparametric registration approach, which simultaneously aligns T1- and T2-weighted MR sequences to CT. This was evaluated and compared with single-parametric approaches. RESULTS: Our results show that deformable registration yielded a better accuracy than rigid registration, without introducing unrealistic deformations. For deformable registration, an average landmark alignment of approximatively 1.7 mm was obtained. For all the regions of interest excluding the cerebellum and the parotids, deformable registration provided a median modified Hausdorff distance of approximatively 1 mm. Similar accuracies were obtained for the single-parameter and multiparameter approaches. CONCLUSIONS: This study demonstrates that deformable registration of head-and-neck CT and MR images is feasible, with overall a significanlty higher accuracy than for rigid registration.

Adaptive image-guided radiotherapy (IGRT) eliminates the risk of biochemical failure caused by the bias of rectal distension in prostate cancer treatment planning: clinical evidence.

PURPOSE: Rectal distension has been shown to decrease the probability of biochemical control. Adaptive image-guided radiotherapy (IGRT) corrects for target position and volume variations, reducing the risk of biochemical failure while yielding acceptable rates of gastrointestinal (GI)/genitourinary (GU) toxicities. METHODS AND MATERIALS: Between 1998 and 2006, 962 patients were treated with computed tomography (CT)-based offline adaptive IGRT. Patients were stratified into low (n = 400) vs. intermediate/high (n = 562) National Comprehensive Cancer Network (NCCN) risk groups. Target motion was assessed with daily CT during the first week. Electronic portal imaging device (EPID) was used to measure daily setup error. Patient-specific confidence-limited planning target volumes (cl-PTV) were then constructed, reducing the standard PTV and compensating for geometric variation of the target and setup errors. Rectal volume (RV), cross-sectional area (CSA), and rectal volume from the seminal vesicles to the inferior prostate (SVP) were assessed on the planning CT. The impact of these volumetric parameters on 5-year biochemical control (BC) and chronic Grades ≥2 and 3 GU and GI toxicity were examined. RESULTS: Median follow-up was 5.5 years. Median minimum dose covering cl-PTV was 75.6 Gy. Median values for RV, CSA, and SVP were 82.8 cm(3), 5.6 cm(2), and 53.3 cm(3), respectively. The 5-year BC was 89% for the entire group: 96% for low risk and 83% for intermediate/high risk (p < 0.001). No statistically significant differences in BC were seen with stratification by RV, CSA, and SVP in quartiles. Maximum chronic Grades ≥2 and 3 GI toxicities were 21.2% and 2.9%, respectively. Respective values for GU toxicities were 15.5% and 4.3%. No differences in GI or GU toxicities were noted when patients were stratified by RV. CONCLUSIONS: Incorporation of adaptive IGRT reduces the risk of geometric miss and results in excellent biochemical control that is independent of rectal volume/distension while maintaining very low rates of chronic GI toxicity.

Split-field helical tomotherapy with or without chemotherapy for definitive treatment of cervical cancer.

OBJECTIVE: The objective of this study was to investigate the chronic toxicity, response to therapy, and survival outcomes of patients with cervical cancer treated with definitive pelvic irradiation delivered by helical tomotherapy (HT), with or without concurrent chemotherapy. METHODS AND MATERIALS: There were 15 patients with a new diagnosis of cervical cancer evaluated in this study from April 2006 to February 2007. The clinical stages of their disease were Stage Ib1 in 3 patients, Ib2 in 3, IIa in 2, IIb in 4, IIIb in 2, and IVa in 1 patient. Fluorodeoxyglucose-positron emission tomography/computed tomography (FDG-PET/CT) simulation was performed in all patients. All patients received pelvic irradiation delivered by HT and high-dose-rate (HDR) brachytherapy. Four patients also received para-aortic irradiation delivered by HT. Thirteen patients received concurrent chemotherapy. Patients were monitored for chronic toxicity using the Common Terminology Criteria for Adverse Events version 3.0 criteria. RESULTS: The median age of the cohort was 51 years (range, 29-87 years), and the median follow-up for all patients alive at time of last follow-up was 35 months. The median overall radiation treatment time was 54 days. One patient developed a chronic Grade 3 GI complication. No other Grade 3 or 4 complications were observed. At last follow-up, 3 patients had developed a recurrence, with 1 patient dying of disease progression. The 3-year progression-free and cause-specific survival estimates for all patients were 80% and 93%, respectively. CONCLUSION: Intensity-modulated radiation therapy delivered with HT and HDR brachytherapy with or without chemotherapy for definitive treatment of cervical cancer is feasible, with acceptable levels of chronic toxicity.