Segmentation of measurable images from standard plane of Graf hip ultrasonograms based on Mask Region-Based Convolutional Neural Network

Abstract

Objectives This study proposed a Mask Region-Based Convolutional Neural Network (R-CNN)-based automatic segmentation to accurately detect the measurable standard plane of Graf hip ultrasonography images via segmentation of the labrum, lower limb of ilium, and the iliac wing. Patients and methods The study examined the hip ultrasonograms of 675 infants (205 males, 470 females; mean age: 7±2.8 weeks; range, 3 to 20 weeks) recorded between January 2011 and January 2018. The standard plane newborn hip ultrasound images were classified according to Graf’s method by an experienced ultrasonographer. The hips were grouped as type 1, type 2a, type 2b, and type 2c-D. Two hundred seventy-five ultrasonograms were utilized as training data, 30 were validation data, and 370 were test data. The three anatomical regions were simultaneously segmented by Mask-R CNN in the test data and defective ultrasonograms. Automatic instance-based segmentation results were compared with the manual segmentation results of an experienced orthopedic expert. Success rates were calculated using Dice and mean average precision (mAP) metrics. Results Of these, 447 Graf type 1, 175 type 2a or 2b, 53 type 2c and D ultrasonograms were utilized. Average success rates with respect to hip types in the whole data were 96.95 and 96.96% according to Dice and mAP methods, respectively. Average success rates with respect to anatomical regions were 97.20 and 97.35% according to Dice and mAP methods, respectively. The highest average success rates were for type 1 hips, with 98.46 and 98.73%, and the iliac wing, with 98.25 and 98.86%, according to Dice and mAP methods, respectively. Conclusion Mask R-CNN is a robust instance-based method in the segmentation of Graf hip ultrasonograms to delineate the standard plane. The proposed method revealed high success in each type of hip for each anatomic region.

Does cranial bone ossification differ in children with developmental dysplasia of the hip?

“…Developmental dysplasia of the hip (DDH) is characterized by the deterioration of the relationship between the acetabulum and the femoral head and represents a wide spectrum ranging from a mildly dysplastic, concentrically located and stable hip to a severely dysplastic and dislocated hip. [ 1 ] In the past, it was a significant cause of disability and, recently thanks to the advanced early diagnostic modalities, particularly hip ultrasonography, that is implemented routinely, DDH can be diagnosed and treated immediately before degenerative arthritis develops. [ 2 , 3 ]…”

Cakirgil method in the surgical treatment of older children with developmental dysplasia of the hip: Mid-term follow-up results of 17 hips and literature review

“…Mask region-based convolutional neural network-based automatic segmentation of anatomical structures of newborn hips from Graf’s ultrasonography images to delineate measurable images provided high success. [ 1 ] Nowadays, due to the increasing rate of deliveries in hospital conditions, routine physical examination, and widespread use of ultrasonography, surgical procedures are performed considerably less; nevertheless, they remain current. Although satisfactory results are obtained after surgical treatment at early ages, the chance of success of the surgical treatment decreases significantly in children over four to six years of age, and surgeries become technically more difficult.…”